Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 619 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4239. Min Range: -0.4239

Max Act: 0.4239. Min Act: -0.0001

Data Index: 758795 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.4239. Min Range: -0.4239

Max Act: 0.4075. Min Act: -0.0001

Data Index: 547799 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.4239. Min Range: -0.4239

Max Act: 0.4131. Min Act: -0.0001

Data Index: 534382 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.4239. Min Range: -0.4239

Max Act: 0.4042. Min Act: -0.0001

Data Index: 1084034 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.4239. Min Range: -0.4239

Max Act: 0.4047. Min Act: -0.0001

Data Index: 604123 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.4239. Min Range: -0.4239

Max Act: 0.4131. Min Act: -0.0001

Data Index: 94966 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.4239. Min Range: -0.4239

Max Act: 0.4030. Min Act: -0.0001

Data Index: 29421 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.4239. Min Range: -0.4239

Max Act: 0.3906. Min Act: -0.0001

Data Index: 277284 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.4239. Min Range: -0.4239

Max Act: 0.3992. Min Act: -0.0001

Data Index: 1085311 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.4239. Min Range: -0.4239

Max Act: 0.3726. Min Act: -0.0001

Data Index: 1485280 (Python Code)

Max Activating Token Index: 1023

Text #10

Max Range: 0.4239. Min Range: -0.4239

Max Act: 0.3775. Min Act: -0.0001

Data Index: 1547847 (Python Code)

Max Activating Token Index: 1023

Text #11

Max Range: 0.4239. Min Range: -0.4239

Max Act: 0.3783. Min Act: -0.0001

Data Index: 761245 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.4239. Min Range: -0.4239

Max Act: 0.3723. Min Act: -0.0001

Data Index: 638771 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.4239. Min Range: -0.4239

Max Act: 0.3654. Min Act: -0.0001

Data Index: 161524 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.4239. Min Range: -0.4239

Max Act: 0.3682. Min Act: -0.0001

Data Index: 1266671 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.4239. Min Range: -0.4239

Max Act: 0.3800. Min Act: -0.0001

Data Index: 940086 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.4239. Min Range: -0.4239

Max Act: 0.3661. Min Act: -0.0001

Data Index: 467710 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.4239. Min Range: -0.4239

Max Act: 0.3529. Min Act: -0.0001

Data Index: 1210678 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.4239. Min Range: -0.4239

Max Act: 0.3632. Min Act: -0.0001

Data Index: 1647599 (Python Code)

Max Activating Token Index: 1023

Text #19

Max Range: 0.4239. Min Range: -0.4239

Max Act: 0.3585. Min Act: -0.0001

Data Index: 327354 (C4 (Web Text))

Max Activating Token Index: 1023